Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only provide readOnlyHint=false, openWorldHint=false, destructiveHint=false, which are minimal. The description adds meaningful behavioral context: it returns presigned PUT URLs, points to Cloudflare R2 storage, warns about sandbox egress requirements, and notes that finalize verifies byte sizes. It doesn't fully describe failure modes or what happens if finalize is never called, but it discloses the key operational behavior beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each earning its place: the first states the core function and mechanism, the second adds the critical egress constraint, the third gives routing and workflow guidance. No filler, no repetition of schema content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description explains the return value (presigned PUT URLs) and the follow-up steps. It covers the key operational constraint (R2 egress) and the alternative for small files. It doesn't mention error cases or the exact shape of the presigned URL response, but for a two-parameter tool with clear workflow context, this is nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50% (name and files are described in the schema). The description adds context about the files parameter (declares files, returns PUT URLs) and the name parameter (auto-suggested if omitted), which complements the schema. It doesn't detail every parameter, but the schema already covers the basics, and the description adds workflow-level meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Start publishing'), a specific resource ('a NEW site'), and the key mechanism (declares files and returns presigned PUT URLs). It also distinguishes itself from publish_site and names the sibling tools for completing or abandoning the flow. This is a clear, specific purpose statement that an agent can act on.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says when to use this tool vs alternatives: 'For small text or base64 files, publish_site is simpler.' It also names the required follow-up tools (finalize_upload, abort_upload), giving the agent a complete workflow context. This is explicit usage guidance with alternatives and exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.